不用数据增强，用投影基学习时间序列表示，性能提升15%-20%
Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections
- 用正交基和过完备帧生成视图，替代传统数据增强
- 在9个时序数据集上比现有自监督方法提升15%-20%
- 适合信号特征复杂、难设计增强的时序任务
自监督学习（SSL）已成为无需标签数据即可学习表示的强大范式。多数SSL方法依赖强而成熟的手工数据增强来生成多样视图进行表示学习。然而，设计这些增强需要领域知识，并隐式引入模型的表示不变性，限制泛化能力。本文提出一种无监督表示学习方法，用正交基和过完备帧生成视图，替代数据增强。我们发现，从正交空间和过完备空间学习到的嵌入位于不同流形上，其几何结构由不同空间表示带来的几何偏差决定。通过联合利用这些互补流形的几何特性，该方法在不通过强增强增加数据多样性的情况下实现更优性能。我们在五个时序任务的九个数据集上验证了该方法的有效性，且在信号特性复杂、难以设计增强的场景中表现突出。相比现有自监督方法，性能提升达15%–20%。源码：https://github.com/eth-siplab/Learning-with-FrameProjections
原文摘要 · Abstract (English)
Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data. Most SSL approaches rely on strong, well-established, handcrafted data augmentations to generate diverse views for representation learning. However, designing such augmentations requires domain-specific knowledge and implicitly imposes representational invariances on the model, which can limit generalization. In this work, we propose an unsupervised representation learning method that replaces augmentations by generating views using orthonormal bases and overcomplete frames. We show that embeddings learned from orthonormal and overcomplete spaces reside on distinct manifolds, shaped by the geometric biases introduced by representing samples in different spaces. By jointly leveraging the complementary geometry of these distinct manifolds, our approach achieves superior performance without artificially increasing data diversity through strong augmentations. We demonstrate the effectiveness of our method on nine datasets across five temporal sequence tasks, where signal-specific characteristics make data augmentations particularly challenging. Without relying on augmentation-induced diversity, our method achieves performance gains of up to 15--20\% over existing self-supervised approaches. Source code: https://github.com/eth-siplab/Learning-with-FrameProjections
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。